Garuda - Garba Rujukan Digital

Implementasi Algoritma Beale-Powell Restarts untuk Prediksi Perkembangan Ekspor Migas-NonMigas di Indonesia GS, Achmad Daengs; Lubis, Mhd. Dicky Syahputra; Mahjudin, M
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 8, No 1 (2024): EDISI MARET
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/j-sakti.v8i1.786

This research aims to implement the Beale-Powell Restarts algorithm in predicting the development of oil and non-oil exports in Indonesia. With the increasing importance of international trade for the economic growth of a country, accurate understanding of export trends becomes crucial for decision-making at the policy level. The data used in this study originates from the value of oil and non-oil exports (in Million US$) in Indonesia obtained from the customs documents of the Directorate General of Customs and Excise (PEB and PIB). The implementation method of the Beale-Powell Restarts algorithm is focused on analyzing and forecasting export development trends. This algorithm is known for its ability to address convergence issues commonly encountered in nonlinear optimization. By applying this algorithm, the research aims to improve the accuracy and precision of predictions, providing valuable insights for economic planning and trade strategy development in Indonesia. The study also includes a comparison of the performance of several different models in prediction, with various models such as 8-5-1, 8-10-1, 8-15-1, 8-20-1, and 8-25-1 being evaluated. The research findings indicate that the best model is 8-5-1, which has the lowest testing Mean Squared Error (MSE) value of 0.00735820154, affirming that the use of the Beale-Powell Restarts algorithm yields better results in predicting the development of oil and non-oil exports in Indonesia compared to other models. It is hoped that the implementation of the Beale-Powell Restarts algorithm will make a significant contribution in assisting stakeholders in formulating more effective and sustainable trade policies to advance the Indonesian economy.

Implementasi Algoritma Beale-Powell Restarts untuk Prediksi Perkembangan Ekspor Migas-NonMigas di Indonesia GS, Achmad Daengs; Lubis, Mhd. Dicky Syahputra; Mahjudin, M
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 8, No 1 (2024): EDISI MARET
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/j-sakti.v8i1.786

This research aims to implement the Beale-Powell Restarts algorithm in predicting the development of oil and non-oil exports in Indonesia. With the increasing importance of international trade for the economic growth of a country, accurate understanding of export trends becomes crucial for decision-making at the policy level. The data used in this study originates from the value of oil and non-oil exports (in Million US$) in Indonesia obtained from the customs documents of the Directorate General of Customs and Excise (PEB and PIB). The implementation method of the Beale-Powell Restarts algorithm is focused on analyzing and forecasting export development trends. This algorithm is known for its ability to address convergence issues commonly encountered in nonlinear optimization. By applying this algorithm, the research aims to improve the accuracy and precision of predictions, providing valuable insights for economic planning and trade strategy development in Indonesia. The study also includes a comparison of the performance of several different models in prediction, with various models such as 8-5-1, 8-10-1, 8-15-1, 8-20-1, and 8-25-1 being evaluated. The research findings indicate that the best model is 8-5-1, which has the lowest testing Mean Squared Error (MSE) value of 0.00735820154, affirming that the use of the Beale-Powell Restarts algorithm yields better results in predicting the development of oil and non-oil exports in Indonesia compared to other models. It is hoped that the implementation of the Beale-Powell Restarts algorithm will make a significant contribution in assisting stakeholders in formulating more effective and sustainable trade policies to advance the Indonesian economy.

Sistem Informasi Penerimaan Siswa Baru dengan Metode SDLC SMK Satria Bingai Lubis, Mhd. Dicky Syahputra; Simanjuntak, Monfride R.; Sembiring, Rosmita Br.
Jurnal Bisantara Informatika Vol. 6 No. 1 (2022): Jurnal Bisantara Informatika Vol 6 No 1 Tahun 2022
Publisher : Akademi Manajemen Informatika dan Komputer PARBINA NUSANTARA Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar

Perkembangan pada dunia komputer khususnya di bidang teknologi dan infromasi sangatlahberkembang dengan pesat, terlebih seiring dengan adanya internet. Seiring dengan kemajuan teknologi yang ada pada saat ini, beberapa instansi-instansi baik perusahaan-perusahaan danlembaga lainnya dan masyarakat berupaya memanfaatkan teknologi tersebut, dapat dilihat darisegi perangkat lunak (software) maupun perangkat keras (hardware) dan juga salah satupenerapan pengolahan data informasi yang terperinci disediakan oleh beberapa paket aplikasiyang ada pada saat ini. Hasil pengolahan tersebut menunjukkan gambaran bahwa duniainformasi ini sangat berguna untuk setiap orang, dimana beberapa orang tersebut dapatmenerima informasi-informasi yang di inginkan secara mudah dan cepat. Informasi-informasiyang di berikan secara mudah bagi penggunaannya melalui internet, dimana dunia internetsangatlah berpengaruh bagi setiap orang. Karena dengan adanya layanan internet, orangorang dapat dengan mudah menerima informasi-informasi apa saja yang di inginkan yangdikemas dalam paket website. Website merupakan sarana dimana orang dapat melihatlangsung informasi yang ada di dalamnya dengan cara mudah, simpel, cepat, dan akurat.Untuk itu dalam kesempatan ini, penulis ingin sedikit memberikan penjelasan tentang tata carapembuatan website itu sendiri dan dimana kita bisa memperolehnya

Klasifikasi Kualitas Produk Mesin Pertanian Berdasarkan Evaluasi Kinerja Algoritma Random Forest Hakim, Irma; Asdi, Asdi; Lubis, Mhd. Dicky Syahputra; Harahap, Mely Novasari; Bara, Lokot Ridwan Batu
Kesatria : Jurnal Penerapan Sistem Informasi (Komputer dan Manajemen) Vol 6, No 1 (2025): Edisi Januari
Publisher : LPPM STIKOM Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/kesatria.v6i1.577

This study aims to classify product quality in the agricultural industry using the Random Forest algorithm. The data used includes various inspection result parameters, such as dimensions, weight, product color, quality status, defect image, inspection time, temperature, machine speed, and indicator lights. The model is developed to classify products into "good" and "defective" categories, and is evaluated based on accuracy metrics and confusion matrix analysis. The results show that the Random Forest model is able to achieve an accuracy of 85% in classifying product quality. Based on the confusion matrix, the model has a perfect prediction rate for good quality products (100% precision) and several misclassifications in the defect category. Feature importance analysis shows that the parameters of inspection time, machine temperature, and defect image are the most significant factors in determining product quality. This study proves that the Random Forest algorithm can be a reliable tool to support the product quality inspection process in the agricultural industry, with further integration into IoT-based systems, this approach can improve the efficiency of the inspection process, reduce manual errors, and ensure more consistent product quality standards.

DESIGN PERANCANGAN SISTEM INFORMASI WEBSITE PENJUALAN KOPI BERBASIS WEB MENGGUNAKAN TEXT EDITOR VISUAL STUDIO CODE Lubis, Mhd. Dicky Syahputra
JURNAL WIDYA Vol. 6 No. 1 (2025): Jurnal Widya (April 2025)
Publisher : Akademi Manajemen Informatika dan Komputer Widya Loka Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54593/awl.v6i1.144

Dalam era digital yang semakin berkembang, kebutuhan akan sistem informasi yang efektif dan efisien menjadi sangat penting bagi bisnis. Penelitian ini bertujuan untuk merancang dan mengimplementasikan sistem informasi penjualan kopi berbasis web yang dapat membantu pengelolaan data penjualan, stok barang, dan interaksi dengan pelanggan. Sistem ini dikembangkan menggunakan Visual Studio Code sebagai lingkungan pengembangan utama, dengan memanfaatkan berbagai teknologi web seperti HTML, CSS, JavaScript, dan PHP untuk backend. Hasil dari penelitian ini adalah sebuah sistem informasi yang user-friendly, mampu mengelola data secara real-time, dan dapat diakses dari berbagai perangkat. Implementasi sistem ini diharapkan dapat meningkatkan efisiensi operasional dan kepuasan pelanggan dalam bisnis penjualan kopi.

Workshop Pembuatan Konten Media Sosial dengan Aplikasi Canva untuk Meningkatkan Daya Saing Produk Lokal Sianturi, Fricles Ariwisanto; Sitio, Arjon Samuel; Legito, Legito; Lubis, Mhd. Dicky Syahputra; Afni, Nurul
ARembeN Jurnal Pengabdian Multidisiplin Vol. 3 No. 1 (2025): ARemBeN Edisi Juni
Publisher : CV. Ro Bema

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69688/aremben.v3i1.141

Workshop ini bertujuan untuk meningkatkan daya saing produk lokal melalui pelatihan pembuatan konten media sosial yang menarik dan efektif menggunakan aplikasi Canva. Dalam era digital, kemampuan pelaku UMKM dalam memasarkan produk secara visual sangat menentukan keberhasilan branding dan penjualan. Metode kegiatan yang digunakan adalah pelatihan partisipatif yang mencakup pemaparan materi, demonstrasi penggunaan Canva, praktik langsung pembuatan konten, serta sesi evaluasi. Peserta workshop terdiri dari pelaku UMKM lokal yang memiliki keterbatasan dalam keterampilan desain grafis. Hasil kegiatan menunjukkan bahwa 90% peserta mengalami peningkatan pemahaman dalam menggunakan Canva, dan 85% berhasil membuat minimal tiga konten promosi yang layak dipublikasikan di media sosial. Selain itu, peserta juga menunjukkan peningkatan kepercayaan diri dalam mengelola akun bisnis mereka secara mandiri. Simpulan dari kegiatan ini adalah bahwa pelatihan pembuatan konten digital menggunakan aplikasi yang mudah diakses seperti Canva dapat menjadi strategi efektif dalam meningkatkan kualitas pemasaran produk lokal dan memperluas jangkauan pasar UMKM secara digital.

Optimizing Natural Language Processing Using ChatGPT for Automated Question and Answer Systems in Public Services Lubis, Mhd. Dicky Syahputra; Sabila, Puji Chairu
International Journal of Information System and Innovative Technology Vol. 4 No. 2 (2025): December
Publisher : Geviva Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63322/y3d3yr10

The use of artificial intelligence (AI) technology is growing rapidly in various sectors, including public services. One of the main challenges in digital public services is how to provide answers that are fast, accurate, and easy for the public to understand. Natural Language Processing (NLP) is key in the development of automated question-and-answer systems. This study evaluates and optimizes the use of ChatGPT as an NLP model in a question-and-answer-based public service system. The methods used include literature review, system design, prototype implementation, and performance evaluation based on accuracy, response speed, and user satisfaction. The results show that ChatGPT can increase answer accuracy by up to 88%, reduce the average response time to 2.9 seconds, and increase user satisfaction to 85%. The system is also able to adapt its language style to make it more understandable to the public. These findings indicate that ChatGPT can be effectively integrated into digital public services, with important considerations regarding ethics, data security, and bias mitigation.

ANALISIS SEGMENTASI PELANGGAN E-COMMERCE MENGGUNAKAN K-MEANS DAN AI UNTUK STRATEGI PEMASARAN PERSONALISASI Muhammad Fauzi; Lubis, Mhd. Dicky Syahputra
JURNAL WIDYA Vol. 6 No. 2 (2025): Jurnal Widya (Oktober 2025)
Publisher : Akademi Manajemen Informatika dan Komputer Widya Loka Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar

The rapid growth of e-commerce platforms presents challenges in understanding customer behaviour to apply targeted marketing strategies. This research combines the K-Means clustering method and Artificial Intelligence (AI) techniques for customer segmentation, enabling personalized marketing. A publicly available e-commerce customer transaction dataset was processed using the Recency, Frequency, Monetary (RFM) model and additional behavioural features. The Elbow and Silhouette methods were applied to determine the optimal number of clusters. The findings identified three main customer segments: “Premium Customers”, “Potential Customers”, and “New/Transient Customers”. AI was used to predict the segment membership of new customers based on historical data. The results are implemented through a simple blue-and-white web interface that provides personalized marketing campaign recommendations for each segment. This research contributes an end-to-end framework from data analysis to practical AI-based segmentation implementation for e-commerce. Keywords: customer segmentation, K-Means clustering, artificial intelligence, e-commerce, personalized marketing.

PERANCANGAN SISTEM INFORMASI BEASISWA DAN REKOMENDASI CALON PENERIMA BEASISWA BERBASIS WEB DI YAYASAN HIDUP MANDIRI AWALI SEMANGAT (HIMNAS) Hulu, Alirman; Lubis, Mhd. Dicky Syahputra; Muhammad. Fauzi
JURNAL WIDYA Vol. 6 No. 2 (2025): Jurnal Widya (Oktober 2025)
Publisher : Akademi Manajemen Informatika dan Komputer Widya Loka Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar

The development of information technology has significantly impacted various fields, including education. The Hidup Mandiri Awali Semangat (HIMNAS) Foundation is an institution that provides scholarship programs for both outstanding and underprivileged students. However, the scholarship registration and selection process at HIMNAS is still conducted manually, leading to inefficiencies and data inaccuracies. This study aims to design and develop a web-based scholarship information system to facilitate the registration, selection, and recommendation of scholarship candidates. The research employs the Waterfall software development model, which includes stages such as requirements analysis, system design, implementation, testing, and maintenance. The result is a web-based information system that allows scholarship candidates to register online, upload documents, and track their verification status. Additionally, the system assists administrators in managing applicant data, conducting verification, and generating reports more quickly and accurately. The implementation of this system is expected to make the scholarship selection process at HIMNAS more transparent, efficient, and accessible. Keywords: Scholarship Information System, Scholarship Recommendation, Web, HIMNAS, Waterfall

Title

Found 9 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 9 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 9 Documents
Search